Skip to main content Skip to navigation

M2LADS Demo: A System for Generating Multimodal Learning Analytics Dashboards

Project Overview

The document highlights the M2LADS system, a web-based platform designed to generate multimodal learning analytics dashboards that leverage generative AI in education. By integrating data from various biosensors, M2LADS provides insights into learner engagement and behavior during educational sessions, thereby enhancing the understanding of learning processes. It synchronizes and visualizes biometric and behavioral data, allowing for more effective data analysis and the improvement of educational outcomes. Key applications of M2LADS include helping researchers validate signals, compare performance metrics, and streamline data relabeling efforts. Overall, the system represents a significant advancement in utilizing generative AI to foster better educational experiences and outcomes by offering a comprehensive view of learner interactions and engagement.

Key Applications

M2LADS (System for Generating Multimodal Learning Analytics Dashboards)

Context: Online learning environments with a focus on learner engagement and behavior analysis.

Implementation: The system integrates and synchronizes various biometric data captured during computer-based learning sessions using biosensors.

Outcomes: Provides detailed insights into learner experiences, facilitates data relabeling, and enhances understanding of learner engagement through visualized data.

Challenges: Integration and synchronization of diverse biosensor data, ensuring data integrity and accurate labeling.

Implementation Barriers

Technical Barrier

Integration and synchronization of diverse biosensor data with traditional metrics.

Proposed Solutions: Utilizing a centralized web-based dashboard to process and visualize multimodal data effectively.

Data Privacy Barrier

Ensuring compliance with data protection regulations and maintaining learner privacy.

Proposed Solutions: Anonymizing stored data and assigning unique identifiers to replace personally identifiable information.

Project Team

Alvaro Becerra

Researcher

Roberto Daza

Researcher

Ruth Cobos

Researcher

Aythami Morales

Researcher

Julian Fierrez

Researcher

Contact Information

For information about the paper, please contact the authors.

Authors: Alvaro Becerra, Roberto Daza, Ruth Cobos, Aythami Morales, Julian Fierrez

Source Publication: View Original PaperLink opens in a new window

Project Contact: Dr. Jianhua Yang

LLM Model Version: gpt-4o-mini-2024-07-18

Analysis Provider: Openai

Let us know you agree to cookies